'ecker comments

Repositories
Issues
Comments

Results 2 comments of


                                            'ecker

Problem of reproducing the quality of the speech from "web_UI"

> I managed to generate very decent TTS samples from your web-UI (https://huggingface.co/spaces/ecker/vall-e) Huh, I could have sworn the HF space was in a degraded state. Last I checked there...

Problem of reproducing the quality of the speech from "web_UI"

> But still the quality is not comparable to the v1 model. Correct. I think the "reference" model will always have an inherent advantage simply from having a gargantuan amount...